Ed230C Experiments #3 & #4 - Effects of Moral Behavior on Reward

Use the data set exp3-4.dta which can be accessed using the Stata command:

use http://www.gseis.ucla.edu/courses/data/exp3-4a

Fourteen subjects were presented with three different situations involving moral judgement. The situations were presented as a series of scenarios in which an eight year old child displays correct moral behavior in each situation. The outcome measure is the amount of reward that the subject would give to the child in the scenario.

The three scenarios were as follows:

A1) The child finds a wallet with a name in it, but no money. The child turns in the wallet to the principal.

A2) The child finds a wallet with a name in it and $20 in it. The child turns in the wallet and money to the principal.

A3) The child finds a wallet with a no name and $20 in it. The child turns in the wallet and money to the principal.

The order of presentation was counterbalanced such that each of the subjects received the scenarios in a different order.

Half the subjects received prior training in making moral decisions (Group 1), while the other half received no moral training (Group 2). Subjects were randomly assigned to treatment groups.

For the purposes of this assignment you are to analyze the data as two different experiments. The first anova design (experiment #3) tests the differences between the three senarios without accounting for group effects (randomized block design). The second anova design experiment #4) should test both the senario and group effects and any appropriate interactions (split-plot factorial).

If you do any manual computations include them on your computer printout. Be sure to include the following:

1. Draw a schematic representations of each design.

2. Present each of the linear model, explaining all terms.

3. Present the statistical and research hypotheses in an appropriate form.
   (for the split-plot factorial design only)

4. State the assumptions underlying these designs. For each assumption, present logical and/or empirical evidence which bears upon whether the assumption is tennable. Present descriptive statistics and statistical tests when appropriate. Be sure to show your work.

5. Report the results of the two ANOVAs. Be sure to include the ANOVA summary table.

6. Present the expected mean squares, explaining the terms, and showing correctly formed F-ratios.
   (for the split-plot factorial design only)

7. Indicate which post-hoc comparisons, if any, are necessary.
   (for the split-plot factorial design only)

8. Discuss your hypotheses in relation to the two designs, i.e., comparre and contrast the two analyses.

Reading the Data

The following Stata code will read in and properly reshape the dataset.

input subj group reward1 reward2 reward3
  1 1 20 18 25 
  2 1 22 20 24 
  3 1 10 17 20 
  4 1 12 15 18 
  5 1 35 37 40 
  6 1 10 15 15 
  7 1 23 19 25 
  8 2 50 52 60 
  9 2 30 33 33 
 10 2 41 40 46 
 11 2 40 42 44 
 12 2 20 19 20 
 13 2 25 26 32
 14 2 31 32 34 
end
reshape long reward, i(subj) j(scen)

UCLA Department of Education